LaplacianFormer uses a Laplacian kernel with an injective feature map and efficient approximations to achieve linear attention that preserves mid-range interactions better than Gaussian-based linear attention in vision transformers.
Faster Neighborhood Attention: Reducing the O(n^2) Cost of Self Attention at the Threadblock Level , volume =
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
LaplacianFormer:Rethinking Linear Attention with Laplacian Kernel
LaplacianFormer uses a Laplacian kernel with an injective feature map and efficient approximations to achieve linear attention that preserves mid-range interactions better than Gaussian-based linear attention in vision transformers.